INDEX

Explanations

mentions of individuals working in specific roles or positions, often discussing policy or international relations

oai_token-act-pair · gpt-3.5-turbo

references to individuals and their professional affiliations

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Manufacturer

-0.69

 OFFIC

-0.69

amp

-0.66

 toilet

-0.66

 stret

-0.63

 nursery

-0.62

 puberty

-0.61

 ambul

-0.61

rhy

-0.61

 lockout

-0.61

POSITIVE LOGITS

 Brookings

1.39

 nonpartisan

1.13

 libertarian

1.04

negie

1.01

 Cato

1.00

 RAND

0.98

 neocons

0.94

 scholar

0.93

Brook

0.92

partisan

0.92

Activations Density 0.311%

mentions of individuals working in specific roles or positions, often discussing policy or international relations

references to individuals and their professional affiliations

No Comments

No Known Activations